An Empirical Study of Cross-Lingual Transferability in Generative Dialogue State Tracker
Abstract
There has been a rapid development in data-driven task-oriented dialogue systems with the benefit of large-scale datasets. However, the progress of dialogue systems in low-resource languages lags far behind due to the lack of high-quality data. To advance the cross-lingual technology in building dialog systems, DSTC9 introduces the task of cross-lingual dialog state tracking, where we test the DST module in a low-resource language given the rich-resource training dataset. This paper studies the transferability of a cross-lingual generative dialogue state tracking system using a multilingual pre-trained seq2seq model. We experiment under different settings, including joint-training or pre-training on cross-lingual and cross-ontology datasets. We also find out the low cross-lingual transferability of our approaches and provides investigation and discussion.
- Publication:
-
arXiv e-prints
- Pub Date:
- January 2021
- DOI:
- 10.48550/arXiv.2101.11360
- arXiv:
- arXiv:2101.11360
- Bibcode:
- 2021arXiv210111360L
- Keywords:
-
- Computer Science - Computation and Language
- E-Print:
- DSTC9 Workshop - AAAI